© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74541
    Prev
    Next
    INDEX
    Explanations

    Nigerian place/personal names

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on personal names (proper‐noun name tokens) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inmiddels
    -1.63
    similar
    -1.47
    documented
    -1.44
     inp
    -1.41
     incontr
    -1.37
     tornando
    -1.37
    噐
    -1.36
    recently
    -1.35
    tauchen
    -1.35
    ela
    -1.34
    POSITIVE LOGITS
    ?”
    1.54
     Many
    1.45
     Then
    1.39
    1.36
     OF
    1.36
     включая
    1.36
    之以
    1.31
     At
    1.30
    WinForms
    1.30
     like
    1.28
    Activations Density 0.008%

    No Known Activations